rtatoeba 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +4 -1
- data/lib/rtatoeba/version.rb +1 -1
- data/lib/rtatoeba.rb +198 -0
- data/spec/lib/rtatoeba_spec.rb +13 -0
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 153dda082aba7ee24f7df60b826dd1d179f806f0
|
|
4
|
+
data.tar.gz: f1b247b31207be7663abfd13bd1813b891a02020
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: de64c3aedfd9acf0bb121b6ed18a7126552470278e5f9413bfd4feb0f0179edf89d27cc6bfb947df9974aa5c1ed5ea575aaa8fd66cd6c068e377684254779826
|
|
7
|
+
data.tar.gz: 7faa0f439b71e7d06ce84945b7f515204f13152420eca16b553b6819eed93697715e928cf516767c85afa55eab1fd4cce672c90161130ef4faf064c85dd9443a
|
data/README.md
CHANGED
|
@@ -1,4 +1,7 @@
|
|
|
1
1
|
[](https://travis-ci.org/pcboy/rtatoeba)
|
|
2
|
+
[](http://badge.fury.io/rb/rtatoeba)
|
|
3
|
+
[](https://codeclimate.com/github/pcboy/rtatoeba)
|
|
4
|
+
|
|
2
5
|
# Rtatoeba
|
|
3
6
|
|
|
4
7
|
Rtatoeba is a tiny gem to access tatoeba.org which doesn't have an API yet.
|
|
@@ -44,7 +47,7 @@ Or install it yourself as:
|
|
|
44
47
|
]
|
|
45
48
|
}
|
|
46
49
|
|
|
47
|
-
|
|
50
|
+
Note: Lang is in ISO-639-2 format
|
|
48
51
|
## Contributing
|
|
49
52
|
|
|
50
53
|
1. Fork it
|
data/lib/rtatoeba/version.rb
CHANGED
data/lib/rtatoeba.rb
CHANGED
|
@@ -21,11 +21,19 @@ require 'mechanize'
|
|
|
21
21
|
|
|
22
22
|
module Rtatoeba
|
|
23
23
|
class Rtatoeba
|
|
24
|
+
class InvalidLangFormat < ArgumentError; end;
|
|
25
|
+
|
|
24
26
|
def initialize(params={})
|
|
25
27
|
@from = params[:from] || "eng"
|
|
26
28
|
@to = params[:to] || "eng"
|
|
27
29
|
@query = params[:query]
|
|
28
30
|
|
|
31
|
+
if !accepted_langs.keys.include?(params[:from]) ||
|
|
32
|
+
!accepted_langs.keys.include?(params[:to])
|
|
33
|
+
raise InvalidLangFormat,
|
|
34
|
+
"Invalid chosen language (#{params[:from]} / #{params[:to]}).\n" +
|
|
35
|
+
"Accepted langs are:\n" + accepted_langs.to_s
|
|
36
|
+
end
|
|
29
37
|
@agent = Mechanize.new
|
|
30
38
|
end
|
|
31
39
|
|
|
@@ -39,5 +47,195 @@ module Rtatoeba
|
|
|
39
47
|
end
|
|
40
48
|
sentences
|
|
41
49
|
end
|
|
50
|
+
|
|
51
|
+
private
|
|
52
|
+
def accepted_langs
|
|
53
|
+
{
|
|
54
|
+
"abk" => "Abkhaz",
|
|
55
|
+
"afr" => "Afrikaans",
|
|
56
|
+
"ain" => "Ainu",
|
|
57
|
+
"sqi" => "Albanian",
|
|
58
|
+
"arq" => "Algerian Arabic",
|
|
59
|
+
"amh" => "Amharic",
|
|
60
|
+
"grc" => "Ancient Greek",
|
|
61
|
+
"ara" => "Arabic",
|
|
62
|
+
"hye" => "Armenian",
|
|
63
|
+
"ast" => "Asturian",
|
|
64
|
+
"awa" => "Awadhi",
|
|
65
|
+
"aze" => "Azerbaijani",
|
|
66
|
+
"bak" => "Bashkir",
|
|
67
|
+
"eus" => "Basque",
|
|
68
|
+
"bel" => "Belarusian",
|
|
69
|
+
"ben" => "Bengali",
|
|
70
|
+
"ber" => "Berber",
|
|
71
|
+
"bho" => "Bhojpuri",
|
|
72
|
+
"bos" => "Bosnian",
|
|
73
|
+
"bre" => "Breton",
|
|
74
|
+
"bul" => "Bulgarian",
|
|
75
|
+
"yue" => "Cantonese",
|
|
76
|
+
"cat" => "Catalan",
|
|
77
|
+
"cha" => "Chamorro",
|
|
78
|
+
"cbk" => "Chavacano",
|
|
79
|
+
"chr" => "Cherokee",
|
|
80
|
+
"cmn" => "Chinese (Mandarin)",
|
|
81
|
+
"nya" => "Chinyanja",
|
|
82
|
+
"ckt" => "Chukchi",
|
|
83
|
+
"chv" => "Chuvash",
|
|
84
|
+
"cor" => "Cornish",
|
|
85
|
+
"crh" => "Crimean Tatar",
|
|
86
|
+
"hrv" => "Croatian",
|
|
87
|
+
"cycl" => "CycL",
|
|
88
|
+
"ces" => "Czech",
|
|
89
|
+
"dan" => "Danish",
|
|
90
|
+
"nld" => "Dutch",
|
|
91
|
+
"arz" => "Egyptian Arabic",
|
|
92
|
+
"egl" => "Emilian",
|
|
93
|
+
"eng" => "English",
|
|
94
|
+
"epo" => "Esperanto",
|
|
95
|
+
"est" => "Estonian",
|
|
96
|
+
"ewe" => "Ewe",
|
|
97
|
+
"fao" => "Faroese",
|
|
98
|
+
"fin" => "Finnish",
|
|
99
|
+
"fra" => "French",
|
|
100
|
+
"fry" => "Frisian",
|
|
101
|
+
"glg" => "Galician",
|
|
102
|
+
"kat" => "Georgian",
|
|
103
|
+
"deu" => "German",
|
|
104
|
+
"ell" => "Greek",
|
|
105
|
+
"kal" => "Greenlandic",
|
|
106
|
+
"grn" => "Guarani",
|
|
107
|
+
"guj" => "Gujarati",
|
|
108
|
+
"hat" => "Haitian Creole",
|
|
109
|
+
"hau" => "Hausa",
|
|
110
|
+
"haw" => "Hawaiian",
|
|
111
|
+
"heb" => "Hebrew",
|
|
112
|
+
"hil" => "Hiligaynon",
|
|
113
|
+
"mrj" => "Hill Mari",
|
|
114
|
+
"hin" => "Hindi",
|
|
115
|
+
"hun" => "Hungarian",
|
|
116
|
+
"isl" => "Icelandic",
|
|
117
|
+
"ido" => "Ido",
|
|
118
|
+
"ind" => "Indonesian",
|
|
119
|
+
"ina" => "Interlingua",
|
|
120
|
+
"ile" => "Interlingue",
|
|
121
|
+
"acm" => "Iraqi Arabic",
|
|
122
|
+
"gle" => "Irish",
|
|
123
|
+
"ita" => "Italian",
|
|
124
|
+
"jpn" => "Japanese",
|
|
125
|
+
"jav" => "Javanese",
|
|
126
|
+
"jdt" => "Juhuri (Judeo-Tat)",
|
|
127
|
+
"xal" => "Kalmyk",
|
|
128
|
+
"kaz" => "Kazakh",
|
|
129
|
+
"kha" => "Khasi",
|
|
130
|
+
"khm" => "Khmer",
|
|
131
|
+
"kin" => "Kinyarwanda",
|
|
132
|
+
"tlh" => "Klingon",
|
|
133
|
+
"ksh" => "Kölsch",
|
|
134
|
+
"kor" => "Korean",
|
|
135
|
+
"avk" => "Kotava",
|
|
136
|
+
"kum" => "Kumyk",
|
|
137
|
+
"kur" => "Kurdish",
|
|
138
|
+
"kir" => "Kyrgyz",
|
|
139
|
+
"lld" => "Ladin",
|
|
140
|
+
"lad" => "Ladino",
|
|
141
|
+
"lkt" => "Lakota",
|
|
142
|
+
"lao" => "Lao",
|
|
143
|
+
"lat" => "Latin",
|
|
144
|
+
"lvs" => "Latvian",
|
|
145
|
+
"lzh" => "Literary Chinese",
|
|
146
|
+
"lit" => "Lithuanian",
|
|
147
|
+
"liv" => "Livonian",
|
|
148
|
+
"jbo" => "Lojban",
|
|
149
|
+
"nds" => "Low Saxon",
|
|
150
|
+
"dsb" => "Lower Sorbian",
|
|
151
|
+
"ltz" => "Luxembourgish",
|
|
152
|
+
"mkd" => "Macedonian",
|
|
153
|
+
"mlg" => "Malagasy",
|
|
154
|
+
"zsm" => "Malay",
|
|
155
|
+
"mal" => "Malayalam",
|
|
156
|
+
"mlt" => "Maltese",
|
|
157
|
+
"mgm" => "Mambae",
|
|
158
|
+
"mri" => "Maori",
|
|
159
|
+
"mar" => "Marathi",
|
|
160
|
+
"mhr" => "Meadow Mari",
|
|
161
|
+
"enm" => "Middle English",
|
|
162
|
+
"frm" => "Middle French",
|
|
163
|
+
"nan" => "Min Nan Chinese",
|
|
164
|
+
"mnw" => "Mon",
|
|
165
|
+
"mon" => "Mongolian",
|
|
166
|
+
"nah" => "Nahuatl",
|
|
167
|
+
"nav" => "Navajo",
|
|
168
|
+
"npi" => "Nepali",
|
|
169
|
+
"nog" => "Nogai",
|
|
170
|
+
"nob" => "Norwegian (Bokmål)",
|
|
171
|
+
"non" => "Norwegian (Nynorsk)",
|
|
172
|
+
"nov" => "Novial",
|
|
173
|
+
"oci" => "Occitan",
|
|
174
|
+
"orv" => "Old East Slavic",
|
|
175
|
+
"ang" => "Old English",
|
|
176
|
+
"prg" => "Old Prussian",
|
|
177
|
+
"tpw" => "Old Tupi",
|
|
178
|
+
"oss" => "Ossetian",
|
|
179
|
+
"ota" => "Ottoman Turkish",
|
|
180
|
+
"pdc" => "Pennsylvania German",
|
|
181
|
+
"pes" => "Persian",
|
|
182
|
+
"pcd" => "Picard",
|
|
183
|
+
"pms" => "Piedmontese",
|
|
184
|
+
"ppl" => "Pipil",
|
|
185
|
+
"pol" => "Polish",
|
|
186
|
+
"por" => "Portuguese",
|
|
187
|
+
"pan" => "Punjabi (Eastern)",
|
|
188
|
+
"pnb" => "Punjabi (Western)",
|
|
189
|
+
"que" => "Quechua",
|
|
190
|
+
"qya" => "Quenya",
|
|
191
|
+
"ron" => "Romanian",
|
|
192
|
+
"roh" => "Romansh",
|
|
193
|
+
"rus" => "Russian",
|
|
194
|
+
"san" => "Sanskrit",
|
|
195
|
+
"gla" => "Scottish Gaelic",
|
|
196
|
+
"srp" => "Serbian",
|
|
197
|
+
"wuu" => "Shanghainese",
|
|
198
|
+
"sna" => "Shona",
|
|
199
|
+
"shs" => "Shuswap",
|
|
200
|
+
"scn" => "Sicilian",
|
|
201
|
+
"sjn" => "Sindarin",
|
|
202
|
+
"sin" => "Sinhala",
|
|
203
|
+
"slk" => "Slovak",
|
|
204
|
+
"slv" => "Slovenian",
|
|
205
|
+
"som" => "Somali",
|
|
206
|
+
"spa" => "Spanish",
|
|
207
|
+
"swh" => "Swahili",
|
|
208
|
+
"swe" => "Swedish",
|
|
209
|
+
"tgl" => "Tagalog",
|
|
210
|
+
"tgk" => "Tajik",
|
|
211
|
+
"tam" => "Tamil",
|
|
212
|
+
"tat" => "Tatar",
|
|
213
|
+
"tel" => "Telugu",
|
|
214
|
+
"tet" => "Tetun",
|
|
215
|
+
"tha" => "Thai",
|
|
216
|
+
"bod" => "Tibetan",
|
|
217
|
+
"tpi" => "Tok Pisin",
|
|
218
|
+
"toki" => "Toki Pona",
|
|
219
|
+
"tur" => "Turkish",
|
|
220
|
+
"tuk" => "Turkmen",
|
|
221
|
+
"udm" => "Udmurt",
|
|
222
|
+
"ukr" => "Ukrainian",
|
|
223
|
+
"hsb" => "Upper Sorbian",
|
|
224
|
+
"urd" => "Urdu",
|
|
225
|
+
"uig" => "Uyghur",
|
|
226
|
+
"uzb" => "Uzbek",
|
|
227
|
+
"vie" => "Vietnamese",
|
|
228
|
+
"vol" => "Volapük",
|
|
229
|
+
"wln" => "Walloon",
|
|
230
|
+
"cym" => "Welsh",
|
|
231
|
+
"xho" => "Xhosa",
|
|
232
|
+
"sah" => "Yakut",
|
|
233
|
+
"yid" => "Yiddish",
|
|
234
|
+
"yor" => "Yoruba",
|
|
235
|
+
"zza" => "Zaza",
|
|
236
|
+
"zul" => "Zulu"
|
|
237
|
+
}
|
|
238
|
+
|
|
239
|
+
end
|
|
42
240
|
end
|
|
43
241
|
end
|
data/spec/lib/rtatoeba_spec.rb
CHANGED
|
@@ -22,5 +22,18 @@ describe Rtatoeba do
|
|
|
22
22
|
it "should return sample sentences" do
|
|
23
23
|
tatoe = Rtatoeba::Rtatoeba.new(from: 'eng', to: 'kor', query: 'hello')
|
|
24
24
|
expect(tatoe.sentences).not_to be_empty
|
|
25
|
+
expect(tatoe.sentences.values.any?(&:empty?)).to eql(false)
|
|
26
|
+
tatoe = Rtatoeba::Rtatoeba.new(from: 'eng', to: 'fra', query: 'monday')
|
|
27
|
+
expect(tatoe.sentences).not_to be_empty
|
|
28
|
+
expect(tatoe.sentences.values.any?(&:empty?)).to eql(false)
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
it "should gives an error if lang is incorrect" do
|
|
32
|
+
expect{
|
|
33
|
+
Rtatoeba::Rtatoeba.new(from: 'english', to: 'fra', query: 'hello')
|
|
34
|
+
}.to raise_error(Rtatoeba::Rtatoeba::InvalidLangFormat)
|
|
35
|
+
expect{
|
|
36
|
+
Rtatoeba::Rtatoeba.new(from: 'en', to: 'french', query: 'hello')
|
|
37
|
+
}.to raise_error(Rtatoeba::Rtatoeba::InvalidLangFormat)
|
|
25
38
|
end
|
|
26
39
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: rtatoeba
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- David Hagege
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2015-09-
|
|
11
|
+
date: 2015-09-09 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: mechanize
|